137 citations · 214 across the 22 of their papers we have counts for
23 papers
Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective
Chenye Ke, Zirui Liu, Qi Liu +4
Detecting pretraining data in large language models is challenging because high likelihood can reflect either training exposure or strong generalization. In the joint space of pred…
Incorporating Cognitive Load and Knowledge Transfer for Multi-Domain Knowledge Tracing
Haotian Zhang, Shucun Wang, Jinze Wu +6
Knowledge Tracing (KT) aims to assess students' dynamic knowledge states from their learning histories. While most existing KT methods focus on single-domain learning with notable…
GeoDecider: An Evidence-Grounded Agent for Geological Interpretation via Deliberative Reasoning
Xiaoyu Tao, Mingyue Cheng, Jiahao Wang +6
Geological interpretation infers subsurface properties and structures from indirect geophysical observations. Well-log classification provides a measurable setting by assigning geo…
CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities
Daoyu Wang, Qingchuan Li, Mingyue Cheng +6
Reinforcement learning (RL) has become a key technique for improving the agentic capabilities of large language models (LLMs). Although critic-free methods such as GRPO are increas…
CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
Jiayu Liu, Zhenya Huang, Wei Dai +7
Although large language models (LLMs) show promise in solving complex mathematical tasks, existing evaluation paradigms rely solely on a coarse measure of overall answer accuracy,…
From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation
Cheng Cheng, Zhenya Huang, Guanhao Zhao +5
Automatically generating high-quality mathematical problems that align with educational objectives is a crucial task in NLP-based educational technology. Traditional generation met…
am-ELO: A Stable Framework for Arena-based LLM Evaluation
Zirui Liu, Jiatong Li, Yan Zhuang +5
Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating sy…
MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers
Lili Zhao, Qi Liu, Wei Chen +5
Empirical Risk Minimization (ERM) models often rely on spurious correlations between features and labels during the learning process, leading to shortcut learning behavior that und…
CursorCore: Assist Programming through Aligning Anything
Hao Jiang, Qi Liu, Rui Li +2
Large language models have been successfully applied to programming assistance tasks, such as code completion, code insertion, and instructional code editing. However, these applic…
ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models
Yuqing Huang, Rongyang Zhang, Xuesong He +15
There is a growing interest in the role that LLMs play in chemistry which lead to an increased focus on the development of LLMs benchmarks tailored to chemical domains to assess th…
A Survey of Models for Cognitive Diagnosis: New Developments and Future Directions
Fei Wang, Weibo Gao, Qi Liu +8
Cognitive diagnosis has been developed for decades as an effective measurement tool to evaluate human cognitive status such as ability level and knowledge mastery. It has been appl…
EduNLP: Towards a Unified and Modularized Library for Educational Resources
Zhenya Huang, Yuting Ning, Longhu Qin +8
Educational resource understanding is vital to online learning platforms, which have demonstrated growing applications recently. However, researchers and developers always struggle…
Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process
Tong Xiao, Jiayu Liu, Zhenya Huang +4
Geometry Problem Solving (GPS), which is a classic and challenging math problem, has attracted much attention in recent years. It requires a solver to comprehensively understand bo…
Survey of Computerized Adaptive Testing: A Machine Learning Perspective
Yan Zhuang, Qi Liu, Haoyang Bi +12
Computerized Adaptive Testing (CAT) offers an efficient and personalized method for assessing examinee proficiency by dynamically adjusting test questions based on individual perfo…
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing
Liyang He, Zhenya Huang, Jiayu Liu +4
Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent…
Unified Uncertainty Estimation for Cognitive Diagnosis Models
Fei Wang, Qi Liu, Enhong Chen +4
Cognitive diagnosis models have been widely used in different areas, especially intelligent education, to measure users' proficiency levels on knowledge concepts, based on which us…
Generative Input: Towards Next-Generation Input Methods Paradigm
Keyu Ding, Yongcan Wang, Zihang Xu +4
Since the release of ChatGPT, generative models have achieved tremendous success and become the de facto approach for various NLP tasks. However, its application in the field of in…
Position: AI Evaluation Should Learn from How We Test Humans
Yan Zhuang, Qi Liu, Zachary A. Pardos +5
As AI systems continue to evolve, their rigorous evaluation becomes crucial for their development and deployment. Researchers have constructed various large-scale benchmarks to det…
Towards a Holistic Understanding of Mathematical Questions with Contrastive Pre-training
Yuting Ning, Zhenya Huang, Xin Lin +4
Understanding mathematical questions effectively is a crucial task, which can benefit many applications, such as difficulty estimation. Researchers have drawn much attention to des…
Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing
Haoyang Bi, Haiping Ma, Zhenya Huang +5
Computerized Adaptive Testing (CAT) is emerging as a promising testing application in many scenarios, such as education, game and recruitment, which targets at diagnosing the knowl…
Neural Cognitive Diagnosis for Intelligent Education Systems
Fei Wang, Qi Liu, Enhong Chen +5
Cognitive diagnosis is a fundamental issue in intelligent education, which aims to discover the proficiency level of students on specific knowledge concepts. Existing approaches us…
QuesNet: A Unified Representation for Heterogeneous Test Questions
Yu Yin, Qi Liu, Zhenya Huang +4
Understanding learning materials (e.g. test questions) is a crucial issue in online learning systems, which can promote many applications in education domain. Unfortunately, many s…
Exploiting Cognitive Structure for Adaptive Learning
Qi Liu, Shiwei Tong, Chuanren Liu +4
Adaptive learning, also known as adaptive teaching, relies on learning path recommendation, which sequentially recommends personalized learning items (e.g., lectures, exercises) to…